去重-pd.duplicated

# 去重 .duplicated

s = pd.Series([1,1,1,1,2,2,2,3,4,5,5,5,5])
print(s.duplicated())
print(s[s.duplicated() == False])
print('-----')
# 判断是否重复
# 通过布尔判断，得到不重复的值

s_re = s.drop_duplicates()
print(s_re)
print('-----')
# drop.duplicates移除重复
# inplace参数：是否替换原值，默认False

df = pd.DataFrame({'key1':['a','a',3,4,5],
                  'key2':['a','a','b','b','c']})
print(df.duplicated())
print(df['key2'].duplicated())
# Dataframe中使用duplicated